Bachelor/Master thesis: Illumination Compensation in Surgical Scenes
Thesis by:Advisor: Nassir Navab
Supervision by: Séverine Habert
Due date: now
Background:
Due to strong lights present in the operating room, specular highlights are present on the video stream captured by CamC?, especially the tools because of their high reflective property(metal), or on the patient body(glossy texture) or on the doctor gloves. Those strong specular highlights are a disturbance for the doctors because they hide or minimize the important information of the surgical scene.
In endoscopic surgery, specular highlight removal has already been studied in order to improve the visualization or as pre-processing for further algorithms such as tool tracking. The type of specular highlights in endoscopic images are similar as the ones in CamC? visualization, they are due to a strong light at the tip of the endoscope and are present on the tissues and tools. The highlights can be easily segmented in order to remove them from the regions of interest or either to inpaint them in order to improve to the surgeon visualization.
Requirements:
Image processing skill, experience with machine learning would be a plusObjectives:
The goal of this project is first to segment the specular highlights and then to inpaint them such as they retrieve their original textures and does not disturb the doctor anymore when using CamC?.Methods:
- WP1: Analysis of the literature about specular removal and inpainting methods
- WP2: Automatic segmentation method for specular highlights
- WP3: Inpainting of the segmented areas
- WP4: Validation of the proposed workflow with our clinic partners
| Students.ProjectForm | |
|---|---|
| Title: | Illumination Compensation in Surgical Scenes |
| Abstract: | Due to strong lights present in the operating room, specular highlights are present on the video stream captured by CamC?, especially the tools because of their high reflective property(metal), or on the patient (glossy texture) body or on the doctor gloves. Those strong specular highlights are a disturbance for the doctors because they hide or minimize the important information of the surgical scene. In endoscopy surgery, specular highlight removal has already been studied in order to improve the visualization or as pre-processing for further algorithms such as tool tracking. Those regions can be easily segmented in order to remove them from the regions of interest or either inpainted in order to improve to withdraw those artefacts. The type of specular highlights in endoscopic images are similar as the ones in CamC? visualization, they are due to a strong light at the tip of the endoscope and are present on the tissues and tools. |
| Student: | Ivan Lebedev |
| Director: | Nassir Navab |
| Supervisor: | Séverine Habert,Pascal Fallavollita |
| Type: | DA/MA/BA |
| Area: | Medical Augmented Reality |
| Status: | finished |
| Start: | now |
| Finish: | |
| Thesis (optional): | |
| Picture: | |